Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375868832> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4375868832 abstract "Automatic Cued Speech Recognition (ACSR) provides an intelligent human-machine interface for visual communications, where the Cued Speech (CS) system utilizes lip movements and hand gestures to code spoken language for hearing-impaired people. Previous ACSR approaches often utilize direct feature concatenation as the main fusion paradigm. However, the asynchronous modalities (i.e., lip, hand shape and hand position) in CS may cause interference for feature concatenation. To address this challenge, we propose a transformer based cross-modal mutual learning framework to prompt multi-modal interaction. Compared with the vanilla self-attention, our model forces modality-specific information of different modalities to pass through a modality-invariant codebook, concatenating linguistic representations with tokens of each modality. Then the shared linguistic knowledge is used to re-synchronize multi-modal sequences. Moreover, we establish a novel large-scale multi-speaker CS dataset for Mandarin Chinese. To our knowledge, this is the first work on ACSR for Mandarin Chinese. Extensive experiments are conducted for different languages (i.e., Chinese, French, and British English). Results demonstrate that our model exhibits superior recognition performance to the state-of-the-art by a large margin." @default.
- W4375868832 created "2023-05-10" @default.
- W4375868832 creator A5020147975 @default.
- W4375868832 creator A5063481044 @default.
- W4375868832 date "2023-06-04" @default.
- W4375868832 modified "2023-10-02" @default.
- W4375868832 title "Cross-Modal Mutual Learning for Cued Speech Recognition" @default.
- W4375868832 cites W2799813293 @default.
- W4375868832 cites W2888888638 @default.
- W4375868832 cites W2972504708 @default.
- W4375868832 cites W2985525390 @default.
- W4375868832 cites W2998687373 @default.
- W4375868832 cites W3008402854 @default.
- W4375868832 cites W3113399631 @default.
- W4375868832 cites W3162293946 @default.
- W4375868832 cites W3196404295 @default.
- W4375868832 cites W3196826198 @default.
- W4375868832 cites W4225685860 @default.
- W4375868832 cites W4283798744 @default.
- W4375868832 cites W4319586818 @default.
- W4375868832 doi "https://doi.org/10.1109/icassp49357.2023.10095271" @default.
- W4375868832 hasPublicationYear "2023" @default.
- W4375868832 type Work @default.
- W4375868832 citedByCount "0" @default.
- W4375868832 crossrefType "proceedings-article" @default.
- W4375868832 hasAuthorship W4375868832A5020147975 @default.
- W4375868832 hasAuthorship W4375868832A5063481044 @default.
- W4375868832 hasBestOaLocation W43758688321 @default.
- W4375868832 hasConcept C114614502 @default.
- W4375868832 hasConcept C127759330 @default.
- W4375868832 hasConcept C138885662 @default.
- W4375868832 hasConcept C138954614 @default.
- W4375868832 hasConcept C144024400 @default.
- W4375868832 hasConcept C154945302 @default.
- W4375868832 hasConcept C185592680 @default.
- W4375868832 hasConcept C188027245 @default.
- W4375868832 hasConcept C204321447 @default.
- W4375868832 hasConcept C207347870 @default.
- W4375868832 hasConcept C2779903281 @default.
- W4375868832 hasConcept C2780226545 @default.
- W4375868832 hasConcept C28490314 @default.
- W4375868832 hasConcept C33923547 @default.
- W4375868832 hasConcept C36289849 @default.
- W4375868832 hasConcept C41008148 @default.
- W4375868832 hasConcept C41895202 @default.
- W4375868832 hasConcept C71139939 @default.
- W4375868832 hasConcept C83195618 @default.
- W4375868832 hasConcept C87619178 @default.
- W4375868832 hasConceptScore W4375868832C114614502 @default.
- W4375868832 hasConceptScore W4375868832C127759330 @default.
- W4375868832 hasConceptScore W4375868832C138885662 @default.
- W4375868832 hasConceptScore W4375868832C138954614 @default.
- W4375868832 hasConceptScore W4375868832C144024400 @default.
- W4375868832 hasConceptScore W4375868832C154945302 @default.
- W4375868832 hasConceptScore W4375868832C185592680 @default.
- W4375868832 hasConceptScore W4375868832C188027245 @default.
- W4375868832 hasConceptScore W4375868832C204321447 @default.
- W4375868832 hasConceptScore W4375868832C207347870 @default.
- W4375868832 hasConceptScore W4375868832C2779903281 @default.
- W4375868832 hasConceptScore W4375868832C2780226545 @default.
- W4375868832 hasConceptScore W4375868832C28490314 @default.
- W4375868832 hasConceptScore W4375868832C33923547 @default.
- W4375868832 hasConceptScore W4375868832C36289849 @default.
- W4375868832 hasConceptScore W4375868832C41008148 @default.
- W4375868832 hasConceptScore W4375868832C41895202 @default.
- W4375868832 hasConceptScore W4375868832C71139939 @default.
- W4375868832 hasConceptScore W4375868832C83195618 @default.
- W4375868832 hasConceptScore W4375868832C87619178 @default.
- W4375868832 hasFunder F4320321001 @default.
- W4375868832 hasLocation W43758688321 @default.
- W4375868832 hasLocation W43758688322 @default.
- W4375868832 hasOpenAccess W4375868832 @default.
- W4375868832 hasPrimaryLocation W43758688321 @default.
- W4375868832 hasRelatedWork W13214881 @default.
- W4375868832 hasRelatedWork W1883289659 @default.
- W4375868832 hasRelatedWork W2032843702 @default.
- W4375868832 hasRelatedWork W2046566646 @default.
- W4375868832 hasRelatedWork W2949074159 @default.
- W4375868832 hasRelatedWork W2952745240 @default.
- W4375868832 hasRelatedWork W4310745221 @default.
- W4375868832 hasRelatedWork W4386721968 @default.
- W4375868832 hasRelatedWork W44671426 @default.
- W4375868832 hasRelatedWork W2520379491 @default.
- W4375868832 isParatext "false" @default.
- W4375868832 isRetracted "false" @default.
- W4375868832 workType "article" @default.